Unlock instant, AI-driven research and patent intelligence for your innovation.

Speech recognition device, speech recognition method and speech recognition program

A speech recognition and speech technology, applied in speech recognition, speech analysis, signal devices, etc., can solve problems such as difficult noise distinction

Active Publication Date: 2018-10-09
KK TOSHIBA
View PDF9 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, if a low-volume speech is used in order to reliably obtain speech, it will become more difficult to distinguish it from noise

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Speech recognition device, speech recognition method and speech recognition program
  • Speech recognition device, speech recognition method and speech recognition program
  • Speech recognition device, speech recognition method and speech recognition program

Examples

Experimental program
Comparison scheme
Effect test

no. 1 Embodiment approach

[0031] figure 1 It is a block diagram showing the configuration of the speech recognition device 100 according to the first embodiment. This speech recognition device converts the speech signal collected by the microphone 101 into a digital signal through the converter 102 and inputs it to the signal processor 103 . According to the instruction from the instruction input device 104, the signal processor 103 compares the speech signal with thresholds based on various conditions, deletes signal components smaller than the threshold, performs speech recognition of the speech signal, converts it into text data, and makes the display device 105 for display.

[0032] Regarding the speech recognition device 100 of the above-mentioned configuration, refer to figure 2 , and its speech recognition processing will be described.

[0033] figure 2 It is a flowchart showing the flow of speech recognition processing in the above-mentioned signal processor 103 . The speech recognition ...

no. 2 Embodiment approach

[0039] Next, a speech recognition device according to the second embodiment will be described. In addition, since the speech recognition device according to this embodiment basically has the same configuration as that of the speech recognition device according to the first embodiment, description of the configuration is omitted here.

[0040] image 3 is a flowchart showing the flow of speech recognition processing according to this embodiment, Figure 4A and Figure 4B It is a concrete example. In addition, in image 3 in, right with figure 2 The same processes as those in the first embodiment shown are denoted by the same reference numerals, and different parts will be described here.

[0041] This embodiment includes readjustment processing. That is, in step S22, when the text data is displayed on the display device 105, the user checks the displayed content, and instructs the readjustment process ( Step S23). In this readjustment process, the input of an instructi...

no. 3 Embodiment approach

[0045] Next, a speech recognition device according to a third embodiment will be described. In addition, since the speech recognition device according to this embodiment basically has the same configuration as that of the speech recognition device according to the first embodiment, description of the configuration is omitted here.

[0046] Figure 5 It is a flowchart showing the flow of speech recognition processing according to this embodiment. In addition, in Figure 5 in, right with figure 2 The same processes as those in the first embodiment shown are denoted by the same reference numerals, and different parts will be described here.

[0047] In the present embodiment, during the adjustment process, after the process of step S13, two thresholds (first threshold t1, second threshold t2, t1

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention relates to a speech recognition device, a speech recognition method and a speech recognition program. The speech recognition device according to one embodiment is provided with an acquisition part, an adjusting part and a recognition part. The acquisition part acquires voice and acquires a voice signal. The adjusting part adjusts a threshold to a value which is lower than a sound volume grade of the input voice signal and performs registering. The recognition part reads the registered threshold and compares the threshold with the input voice signal. On the condition that the sound volume grade of the input voice signal is lower than the threshold, the input voice signal is abandoned. On the condition that the sound volume grade of the input voice signal is higher than or equal with the threshold, the input voice signal is recognized as the voice signal of a speaker as a recognition object. Therefore, the speech recognition device which acquires the speech in a user expection range based on interactive adjustment instruction to a user can be supplied.

Description

[0001] This application enjoys priority based on Japanese patent application 2017-054907 (filing date: 03 / 21 / 2017) as the earlier application. This application includes the entire content of the same application by referring to this application. technical field [0002] Embodiments of the present invention relate to a speech recognition device, a speech recognition method, and a speech recognition program. Background technique [0003] The voice recognition device has a function of recording and recognizing the voice of a target speaker with a microphone, and converting the recognition result into a text (text). However, depending on the environment, it may be difficult to distinguish between noise and speech in the background. Especially in the case of recording the voices of multiple people, depending on the distance and / or direction from the microphone, it may be difficult to acquire the voices. In addition, in a room or a conference, even a single person's voice may so...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G10L15/22
CPCG10L15/22G10L25/78G10L2025/786G10L15/20G06F3/167G06F3/165G10L2015/225G10L2015/223B60Q9/007
Inventor 笼岛岳彦
Owner KK TOSHIBA